Jason Kuen

Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation

Image Tokenizer Needs Post-Training

CoT Referring: Improving Localization with Grounded Reasoning in Referring Expression Tasks

LaViDa: A Large Diffusion Model for Vision-Language Understanding

ImageFolder: Autoregressive Image Generation with Folded Tokens

OIDA-QA: A Multimodal Benchmark for Analyzing the Opioid Industry Document Archive

ControlVAR: Exploring Controllable Visual Autoregressive Modeling